#Creating table to present results for question 1 
kable(One)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:7, color="black")

#Creating data set to answer question 1B
Question<-c("2A", "2B", "2C", "2D", "2E", "2F", "2G", "2H", "2I")
Question<-data.frame(Question)
Answer<-c("Value", "Variable", "Value", "Variable", "Value",
          "Value", "Variable", "Variable", "Variable")
Answer<-data.frame(Answer)
Two<-cbind(Question, Answer)

#Creating table to present results
kable(Two)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:9, color="black")  

#Creating data set to answer question 1
Questions<-c("Ratio", "Proportion", "Percentage")
Q10A<-c("105342:630398", "0.1431783", "14.31783%")
Q10B<-c("221:312", "0.4146341", "41.46341%")
Q10C<-c("221:432", "0.338438", "33.8438%")
Questions<-data.frame(Questions)
Q10A<-data.frame(Q10A)
Q10B<-data.frame(Q10B)
Q10C<-data.frame(Q10C)
Q1<-cbind(Questions, Q10A, Q10B, Q10C)
Q1<-dplyr::rename(Q1,"10A"="Q10A", "10B"="Q10B", "10C"="Q10C")

#Creating table to present results
kable(Q1)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:3, color="black")

#Creating data set to answer question 1
Question<-c("11", "12", "13", "14")
Answer<-c("4.765431% Decrease", "4.111168% Decrease", "10.7142857143 Change%", "3:2")
Q2<-cbind(Question, Answer)
Q2<-data.frame(Q2)

#Creating table to present results
kable(Q2)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:4, color="black")

#Uploading dataset
sleep<-datasets::sleep

#Making group variable a factor variable and giving it labels
sleep$group<-factor(sleep$group, levels = c("1","2"),labels=c("Drug One", "Drug Two"))

#Subsetting the data to create summary tables 
d1<-dplyr::filter(sleep, group=="Drug One")
d2<-dplyr::filter(sleep, group=="Drug Two")

#Cacluating summary statistics for the two drugs
DS1<-list("Drug 1" =list("Mean"=~mean(d1$extra),"Median"=~median(d1$extra),"Maximum"=~max(d1$extra), "Minimum"=~min(d1$extra),"Standard Deviation"=~sd(d1$extra)))
DS2<-list("Drug 2" = list("Mean"=~mean(d2$extra),"Median"=~median(d2$extra),"Maximum"=~max(d2$extra), "Minimum"=~min(d2$extra),"Standard Deviation"=~sd(d2$extra)))

#Creating summary tables and renaming the columns to put into my kable table
DS1T<- summary_table(d1, DS1)
DS1T<-data.frame(DS1T)
DS1T<-dplyr::rename(DS1T, "Subjects Drug One (N=10)" = "d1..N...10.")
DS2T<-summary_table(d2, DS2)
DS2T<-data.frame(DS2T)
DS2T<-dplyr::rename(DS2T, "Subjects Drug Two (N=10)" = "d2..N...10.")

#Creating table to present results
kable(DS1T)%>% kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
row_spec(1:5, color="black")

#Creating table to present results
kable(DS2T)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:5, color="black")  

#Creating mean-line that can be used for my histogram 
mg<- ddply(sleep, "group", summarise, mean=mean(extra))

#Creating a histogram plot to compare the two types of drugs
p<-ggplot(sleep, aes(x=extra, colour=group)) + 
  #Altering bindwidth and colour of plot
  geom_histogram(binwidth=1,
                 colour="steelblue1",
                 fill="steelblue1",
                 alpha=0.3)+
  #Changing the names of the title and x-y axis titles
  labs(x="Hours Slept", y="Count",title="Comparing the Effects of Insomnia Drugs")+
  #Presenting two seperate graphs for the drugs
  facet_wrap(~group)+
  #Creating the x-axis scale 
  scale_x_continuous(breaks = seq(from = -1.6, to=5.5, by=1))+
  #Changing the overall colour theme of the plot
  dark_theme_gray()+
  #Removing grid lines on plot
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  #Implementing mean line in graph
  geom_vline(data=mg, aes(xintercept=mean, color=group),
           linetype="dashed")+
  #Removing legend
  theme(legend.position="none")+
  #Changing font size and colour
  font("title", size = 14, colour = "snow")+
  font("xy.title", size = 12, colour = "snow")+
  font("xy.text", color="snow")

#Creating an interactive plot
ggplotly(p)

#Creating a dataset which has country, PR, CL, and status variables
country<-country[-c(1:3),]

#Creating list of title names
titlelist<-c("PR-","CL-","Status-")

#Making the number of titles I want
NoT<- rep(titlelist, 47)

#Making loop that makes column titles for every third column and putting a different
#number after each title (e.g., PR-1, CL-1, Status-1, PR-2, CL-2, Status-2, PR-3, CL-3, Status-3)
titlesloop<- 1:length(NoT)
titlesloop<- as.character(ifelse(mod(titlesloop,3)>0,floor(titlesloop/3)+1,floor(titlesloop/3)))
headers <- c("country",paste0(NoT,titlesloop))
colnames(country) <- paste0(headers, seq_len(ncol(country)))

#Putting all the PR and CL values into separate columns
country1<-tidyr::pivot_longer(country, cols = starts_with("PR"), names_to = "PR2",values_to = "pr")
country2<-tidyr::pivot_longer(country, cols = starts_with("CL"), names_to = "CL2",values_to = "cl")

#Removing unnecessary columns to bind these datasets together
country1<-country1[,-c(2:96)]
country2<-country2[,-c(2:96)]

#Binding datasets 
country<-cbind(country1, country2, all.x=TRUE)
country<-country[,-c(3,5)]

#Creating dataset that has all the years, and removing unnecessary columns
year<-t(year)
year<-as.data.frame(year)
year<-year[-c(1),]
year<-year[,-c(2:208)]
year<-data.frame(year)

#Creating a loop that fills in missing values with the correct year
for(i in 2:length(year$year)) {if (is.na(year$year[i])==TRUE) {year$year[i] <- year$year[i-1] }else{year$year[i] <-year$year[i]}}


#Getting ready to merge datasets and removing duplicates
FH<-select(country, country1)
FH<-merge(FH, year)
FH<-FH%>%distinct()

#Recoding values in dataset
FH$year<- recode(FH$year,"'1983-84'='1983';'1984-85'='1984';'1984-85'='1984';'1984-85'='1984';'1984-85'='1984';'1984-85'='1984';'1985-86'='1985';'1986-87'='1986';'1987-88'='1987';'1988-89'='1988';'1989-90'='1989';'1990-91'='1990';'1991-92'='1991';'1992-93'='1992';'1993-94'='1993';'1994-95'='1994';'1995-96'='1995';'1996-97'='1996';'1997-98'='1997';'1998-99'='1998';'1999-2000'='1999';'2000-01'='2000';'2001-02'='2001';'Jan.-Feb. 1973'='1973';'Jan.-Feb. 1974'='1974';'Jan.-Feb. 1975'='1975';'Jan.-Feb. 1976'='1976';'Jan.-Feb. 1977'='1977'")

#Arrange dataset in alphabetic order and binding datasets
FH<-FH %>% arrange(country1)
country<-select(country, pr, cl)
FH<-cbind(FH, country)

#Removing rows so I can make USSR into Russia
FH<-FH[-c(9043:9071),]
FH<-FH[-c(6769:6786),]

#Recode USSR 
FH$country1<- recode(FH$country1, "'USSR'='Russia'")

#Arrange Russia correctly by year and name
FH<-FH%>% arrange(country1, year)

#Filtering out states that are no longer consider countries
FH$country1<-as.character(FH$country1)
FH<-FH%>%filter(!country1 %in% c("Yugoslavia", "Vietnam, N.", "Vietnam, S.", "Germany, E.", "Germany, W.", "Yemen, N.", "Yemen, S.", "Czechoslovakia", "Serbia and Montenegro"))

#Making PR and CL numeric variables
FH$pr<-as.numeric(FH$pr)

FH$cl<-as.numeric(FH$cl)

#Making a table that shows the number of observations and countries in the dataset 
Question<-c("Number of countries", "Number of observations")
Question<-data.frame(Question)
Answer<-c("195", "9165")
Answer<-data.frame(Answer)
T<-cbind(Question,Answer)

#Creating a table to present results
kable(T)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:2, color="black")

#Creating a combine scores variable and standardizing it on a 7 point scale
FH<-dplyr::mutate(FH, CS = (pr + cl)/2)

#Selecting all years that are 2010
FH1<-FH%>%
  dplyr::filter(year == "2010")%>%
  dplyr::select(-c(2:4))%>%
  dplyr::rename(Ten=CS)

#Selecting all years that are 2020 
FH2<-FH%>%
  dplyr::filter(year == "2020")%>% 
  dplyr::select(-c(2:4))%>% 
  dplyr::rename(Twenty=CS)

#Binding data sets together
FH2<-cbind(FH1, FH2, all.x=TRUE)
FH2<-FH2%>%select(-c(3,5))

#Subtracting each combined score in 2020 by 2010 
FH3<-FH2%>%dplyr::mutate(FH2, DCS = (Twenty-Ten), na.rm=TRUE)%>%
#Removing unnecessary columns
dplyr::select(-c(2:3,5))%>%
#Omiting missing values
na.omit(FH3)%>%
#arranging the lowest values to the top of the dataset
dplyr::arrange(DCS)%>%
#Selecting the countries with the 10 largest declines
dplyr::slice(1:10)%>%
#Renaming column titles
dplyr::rename("Country"="country1", "Declines in Combined Scores" = "DCS")

#Displaying the countries with the top 10 largest declines
kable(FH3)%>%kable_styling(bootstrap_options = c("striped", "hover", "condensed","responsive", "bordered"))%>%
  column_spec(1, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(0, bold=TRUE, background="skyblue", color="black")%>%
  row_spec(1:10, color="black")                                       

#Making boxplot for political right scores
ggplot(FH, aes(x=pr), na.rm=TRUE)+ 
#Changing colour of boxplot
  geom_boxplot(colour="steelblue1",
               fill="steelblue1",
               alpha=0.3)+
#Changing the title and x-y axis labels
  labs(x="Political Rights Score", y="Probability Density",
       title="Boxplot for Political Rights Scores") +
#Creating the scale for the x-axis
  scale_x_continuous(limits = c(0, 7),
                     breaks = seq(from = 1, to=7, by=1))+
#Fliping the plot and x-y axis
  coord_flip()+
#Changing the colour theme of the plot
  dark_theme_gray()+
#Removing gridlines 
    theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
#Changing colour and font size for title and x-y axis
  font("title", size = 14, color = "snow")+
   font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")

#Creating mean line
PRM<-mean(FH$pr, na.rm=TRUE)

#Creating histogram plot
p3<-ggplot(FH, aes(x=pr), na.rm=TRUE)+ 
#Changing colour of plot
  geom_histogram(binwidth=1,
                 color="steelblue1",
                 fill="steelblue1",
                 alpha=0.3)+
#Changing title and x-y axis labels
  labs(x="Political Rights Score", y="Count", title="Histogram for Political Rights Scores")+
#Changing the scale of the x-axis
  scale_x_continuous(breaks= seq(from =1, to=7, by=1))+
#Changing colour theme of plot
  dark_theme_gray()+
#Putting in mean line 
  geom_vline(data=FH, aes(xintercept=PRM),
             linetype="dashed")+
#Removing gridlines 
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
#Changing font and colour of title and x-y axis labels
font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")

#Creating interactive plot
ggplotly(p3)

#Same process as previous boxplot
ggplot(FH, aes(x=cl), na.rm=TRUE)+ 
  geom_boxplot(colour="steelblue1",
               fill="steelblue1",
               alpha=0.3)+
  labs(x="Civil Liberties Score", y="Probability Density", title="Boxplot For Civil Liberties Scores") +
  scale_x_continuous(limits = c(0, 7),
                     breaks = seq(from = 1, to=7, by=1))+
  coord_flip()+
  dark_theme_gray()+
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  font("title", size = 14, color = "snow")+
   font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")

#Same process as previous histogram
CLM<-mean(FH$cl, na.rm=TRUE)
p2<-ggplot(FH, aes(x=cl), na.rm=TRUE)+
  geom_histogram(binwidth=1,
                 color="steelblue1",
                 fill="steelblue1",
                 alpha=0.3)+
  labs(x="Civil Liberties Score", y="Count", title="Histogram for Civil Liberties Scores")+
  scale_x_continuous(breaks= seq(from =1, to=7, by=1))+
  dark_theme_gray()+
  geom_vline(data=FH, aes(xintercept=CLM),
             linetype="dashed")+
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")

ggplotly(p2)

#Making year a character variable
FH$year<-as.character(FH$year)
#Same process as previous boxplot except using viridis package and making a boxplot for each year
ggplot(FH, aes(x=pr, y=year, na.rm=TRUE))+ 
#Using viridis package to change colour for each boxplot 
  geom_boxplot(fill=(viridis(47)), colour="white")+
  labs(title="Boxplot for Political Rights Score Per Year",
       x="Political Rights Score", y="Year") +
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  scale_x_continuous(limits = c(0, 7),
                     breaks = seq(from = 1, to=7, by=1))+
  coord_flip()+
  dark_theme_gray()+
  font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")+
#Flipping the x-axis text to 90 degrees
  theme(axis.text.x = element_text(angle = 90))

#Same process as previous histogram but making a histogram for each year
ggplot(FH, aes(x=pr), na.rm=TRUE)+ 
  geom_histogram(binwidth=1,
                 color="steelblue1",
                 fill="steelblue1",
                 alpha=0.3)+
  labs(x="Civil Liberties Score", y="Count", title="Histogram for Political Rights Score Per Year")+
  scale_x_continuous(breaks= seq(from =1, to=7, by=1))+
  dark_theme_gray()+
    theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")+
#Making sure that the plot shows a histogram for each year
  facet_wrap(~year)

#Same process as per year boxplot but for civil liberties score 
FH$year<-as.character(FH$year)
ggplot(FH, aes(x=cl, y=year, na.rm=TRUE))+ 
  geom_boxplot(fill=(viridis(47)), colour="white")+
  labs(title="Boxplot for Civil Liberties Score Per Year",
       x="Civil Liberties Score", y="Year")+
  scale_x_continuous(limits = c(0, 7),
                     breaks = seq(from = 1, to=7, by=1))+
  coord_flip()+
  dark_theme_gray()+
    theme(axis.text.x = element_text(angle = 90),
          panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")

#Same process as previous histogram but for civil liberties score
ggplot(FH, aes(x=cl), na.rm=TRUE)+ 
  geom_histogram(binwidth=1,
                 color="steelblue1",
                 fill="steelblue1",
                 alpha=0.3)+
  labs(x="Civil Liberties Score", y="Count", title="Histogram for Civil Liberties Score Per Year")+
  scale_x_continuous(breaks= seq(from =1, to=7, by=1))+
  dark_theme_gray()+
    theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())+
  font("title", size = 14, color = "snow")+
  font("xy.title", size = 12, color = "snow")+
  font("xy.text", color="snow")+
  facet_wrap(~year)